Concordance

Query J05-1003 44 >
Negative filter probabilistic, parser 43 >
Sort Right 43 (1,376.7 per million)

measure(ment),6-8-J05-1003,ak	The new <term> model </term> achieved 89.75 % <term> F-measure </term> , a 13 % relative decrease in <term> F-measure error </term> over the <term> baseline model ’s </term> score of 88.2 % .	#8206 The new model achieved 89.75%F-measure, a 13% relative decrease in F-measure error over the baseline model’s score of 88.2%.
other,7-5-J05-1003,ak	We introduce a new method for the <term> reranking task </term> , based on the <term> boosting approach to ranking problems </term> described in Freund et al. ( 1998 ) .	#8131 We introduce a new method for thereranking task, based on the boosting approach to ranking problems described in Freund et al. (1998).
other,30-12-J05-1003,ak	Although the experiments in this article are on <term> natural language parsing ( NLP ) </term> , the approach should be applicable to many other <term> NLP problems </term> which are naturally framed as <term> ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation </term> .	#8331 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed asranking tasks, for example, speech recognition, machine translation, or natural language generation.
tech,36-12-J05-1003,ak	Although the experiments in this article are on <term> natural language parsing ( NLP ) </term> , the approach should be applicable to many other <term> NLP problems </term> which are naturally framed as <term> ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation </term> .	#8337 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example,speech recognition, machine translation, or natural language generation.
tech,39-12-J05-1003,ak	Although the experiments in this article are on <term> natural language parsing ( NLP ) </term> , the approach should be applicable to many other <term> NLP problems </term> which are naturally framed as <term> ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation </term> .	#8340 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition,machine translation, or natural language generation.
tech,8-12-J05-1003,ak	Although the experiments in this article are on <term> natural language parsing ( NLP ) </term> , the approach should be applicable to many other <term> NLP problems </term> which are naturally framed as <term> ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation </term> .	#8309 Although the experiments in this article are onnatural language parsing ( NLP ), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation.
other,10-3-J05-1003,ak	A second <term> model </term> then attempts to improve upon this initial <term> ranking </term> , using additional <term> features </term> of the <term> tree </term> as evidence .	#8064 A second model then attempts to improve upon this initialranking, using additional features of the tree as evidence.
other,11-2-J05-1003,ak	The <term> base parser </term> produces a set of <term> candidate parses </term> for each <term> input sentence </term> , with associated <term> probabilities </term> that define an initial <term> ranking </term> of these <term> parses </term> .	#8039 The base parser produces a set of candidate parses for eachinput sentence, with associated probabilities that define an initial ranking of these parses.
other,19-4-J05-1003,ak	The strength of our approach is that it allows a <term> tree </term> to be represented as an arbitrary set of <term> features </term> , without concerns about how these <term> features </term> interact or overlap and without the need to define a <term> derivation </term> or a <term> generative model </term> which takes these <term> features </term> into account .	#8094 The strength of our approach is that it allows a tree to be represented as an arbitrary set offeatures, without concerns about how these features interact or overlap and without the need to define a derivation or a generative model which takes these features into account.
other,24-2-J05-1003,ak	The <term> base parser </term> produces a set of <term> candidate parses </term> for each <term> input sentence </term> , with associated <term> probabilities </term> that define an initial <term> ranking </term> of these <term> parses </term> .	#8052 The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of theseparses.
model,25-11-J05-1003,ak	We argue that the method is an appealing alternative — in terms of both simplicity and efficiency — to work on <term> feature selection methods </term> within <term> log-linear ( maximum-entropy ) models </term> .	#8295 We argue that the method is an appealing alternative—in terms of both simplicity and efficiency—to work on feature selection methods withinlog-linear ( maximum-entropy ) models.
other,23-9-J05-1003,ak	The article also introduces a new <term> algorithm </term> for the <term> boosting approach </term> which takes advantage of the <term> sparsity </term> of the <term> feature space </term> in the <term> parsing data </term> .	#8249 The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in theparsing data.
lr,8-6-J05-1003,ak	We apply the <term> boosting method </term> to parsing the <term> Wall Street Journal treebank </term> .	#8159 We apply the boosting method to parsing theWall Street Journal treebank.
model,34-7-J05-1003,ak	The method combined the <term> log-likelihood under a baseline model </term> ( that of Collins [ 1999 ] ) with evidence from an additional 500,000 <term> features </term> over <term> parse trees </term> that were not included in the original <term> model </term> .	#8198 The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the originalmodel.
tech,15-10-J05-1003,ak	Experiments show significant efficiency gains for the new <term> algorithm </term> over the obvious implementation of the <term> boosting approach </term> .	#8267 Experiments show significant efficiency gains for the new algorithm over the obvious implementation of theboosting approach.
tech,43-12-J05-1003,ak	Although the experiments in this article are on <term> natural language parsing ( NLP ) </term> , the approach should be applicable to many other <term> NLP problems </term> which are naturally framed as <term> ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term> , or <term> natural language generation </term> .	#8344 Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, ornatural language generation.
other,4-7-J05-1003,ak	The method combined the <term> log-likelihood under a baseline model </term> ( that of Collins [ 1999 ] ) with evidence from an additional 500,000 <term> features </term> over <term> parse trees </term> that were not included in the original <term> model </term> .	#8168 The method combined thelog-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model.
model,2-8-J05-1003,ak	The new <term> model </term> achieved 89.75 % <term> F-measure </term> , a 13 % relative decrease in <term> F-measure error </term> over the <term> baseline model ’s </term> score of 88.2 % .	#8202 The newmodel achieved 89.75% F-measure, a 13% relative decrease in F-measure error over the baseline model’s score of 88.2%.
other,17-3-J05-1003,ak	A second <term> model </term> then attempts to improve upon this initial <term> ranking </term> , using additional <term> features </term> of the <term> tree </term> as evidence .	#8071 A second model then attempts to improve upon this initial ranking, using additional features of thetree as evidence.
tech,13-5-J05-1003,ak	We introduce a new method for the <term> reranking task </term> , based on the <term> boosting approach to ranking problems </term> described in Freund et al. ( 1998 ) .	#8137 We introduce a new method for the reranking task, based on theboosting approach to ranking problems described in Freund et al. (1998).


	in Help